Equivariant Disentangled Transformation for Domain Generalization under Combination Shift

08/03/2022
by   Yivan Zhang, et al.
0

Machine learning systems may encounter unexpected problems when the data distribution changes in the deployment environment. A major reason is that certain combinations of domains and labels are not observed during training but appear in the test environment. Although various invariance-based algorithms can be applied, we find that the performance gain is often marginal. To formally analyze this issue, we provide a unique algebraic formulation of the combination shift problem based on the concepts of homomorphism, equivariance, and a refined definition of disentanglement. The algebraic requirements naturally derive a simple yet effective method, referred to as equivariant disentangled transformation (EDT), which augments the data based on the algebraic structures of labels and makes the transformation satisfy the equivariance and disentanglement requirements. Experimental results demonstrate that invariance may be insufficient, and it is important to exploit the equivariance structure in the combination shift problem.

READ FULL TEXT

page 7

page 9

page 10

page 25

page 26

page 27

page 28

research
11/28/2022

Beyond Invariance: Test-Time Label-Shift Adaptation for Distributions with "Spurious" Correlations

Spurious correlations, or correlations that change across domains where ...
research
11/15/2022

HMOE: Hypernetwork-based Mixture of Experts for Domain Generalization

Due to the domain shift, machine learning systems typically fail to gene...
research
02/13/2023

Predicting Class Distribution Shift for Reliable Domain Adaptive Object Detection

Unsupervised Domain Adaptive Object Detection (UDA-OD) uses unlabelled d...
research
12/05/2018

Towards a Definition of Disentangled Representations

How can intelligent agents solve a diverse set of tasks in a data-effici...
research
06/01/2021

Invariant Policy Learning: A Causal Perspective

In the past decade, contextual bandit and reinforcement learning algorit...
research
05/16/2022

Generalizing to Evolving Domains with Latent Structure-Aware Sequential Autoencoder

Domain generalization aims to improve the generalization capability of m...
research
07/12/2023

Tackling Combinatorial Distribution Shift: A Matrix Completion Perspective

Obtaining rigorous statistical guarantees for generalization under distr...

Please sign up or login with your details

Forgot password? Click here to reset